Publications

Doubly Right Object Recognition: A Why Prompt for Visual Rationales
Chengzhi Mao
Revant Teotia
Amrutha Sundar
Sachit Menon
Junfeng Yang
Xin Wang
Carl Vondrick
Many visual recognition models are evaluated only on their classification accuracy, a metric for which they obtain strong performance. In th… (see more)is paper, we investigate whether computer vision models can also provide correct rationales for their predictions. We propose a “doubly right” object recognition benchmark, where the metric requires the model to simultaneously produce both the right labels as well as the right rationales. We find that state-of-the-art visual models, such as CLIP, often provide incorrect rationales for their categorical predictions. However, by transferring the rationales from language models into visual representations through a tailored dataset, we show that we can learn a “why prompt,” which adapts large visual representations to produce correct rationales. Visualizations and empirical experiments show that our prompts significantly improve performance on doubly right object recognition, in addition to zero-shot transfer to unseen tasks and datasets.
2023-06-17
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (published)
doi.org
arxiv.org
Open-Set Likelihood Maximization for Few-Shot Learning
Malik Boudiaf
Etienne Bennequin
Myriam Tami
Antoine Toubhans
Pablo Piantanida
Celine Hudelot
Ismail Ben Ayed
We tackle the Few-Shot Open-Set Recognition (FSOSR) problem, i.e. classifying instances among a set of classes for which we only have a few … (see more)labeled samples, while simultaneously detecting instances that do not belong to any known class. We explore the popular transductive setting, which leverages the unlabelled query instances at inference. Motivated by the observation that existing transductive methods perform poorly in open-set scenarios, we propose a generalization of the maximum likelihood principle, in which latent scores down-weighing the influence of potential outliers are introduced alongside the usual parametric model. Our formulation embeds supervision constraints from the support set and additional penalties discouraging overconfident predictions on the query set. We proceed with a block-coordinate descent, with the latent scores and parametric model co-optimized alternately, thereby benefiting from each other. We call our resulting formulation Open-Set Likelihood Optimization (OSLO). OSLO is interpretable and fully modular; it can be applied on top of any pre-trained model seamlessly. Through extensive experiments, we show that our method surpasses existing inductive and transductive methods on both aspects of open-set recognition, namely inlier classification and outlier detection. Code is available at https://github.com/ebennequin/few-shot-open-set.
2023-06-17
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (published)
doi.org
arxiv.org
Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss
Anas Mahmoud
Jordan S. K. Hu
Tianshu Kuai
Ali Harakeh
Liam Paull
Steven L. Waslander
An effective framework for learning 3D representations for perception tasks is distilling rich self-supervised image features via contrastiv… (see more)e learning. However, image-to-point representation learning for autonomous driving datasets faces two main challenges: 1) the abundance of self-similarity, which results in the contrastive losses pushing away semantically similar point and image regions and thus disturbing the local semantic structure of the learned representations, and 2) severe class imbalance as pretraining gets dominated by over-represented classes. We propose to alleviate the self-similarity problem through a novel semantically tolerant image-to-point contrastive loss that takes into consideration the semantic distance between positive and negative image regions to minimize contrasting semantically similar point and image regions. Additionally, we address class imbalance by designing a class-agnostic balanced loss that approximates the degree of class imbalance through an aggregate sample-to-samples semantic similarity measure. We demonstrate that our semantically-tolerant contrastive loss with class balancing improves state-of-the-art 2D-to-3D representation learning in all evaluation settings on 3D semantic segmentation. Our method consistently outperforms state-of-the-art 2D-to-3D representation learning frameworks across a wide range of 2D self-supervised pretrained models.
2023-06-17
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (published)
doi.org
arxiv.org
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
Mahmoud Assran
Quentin Duval
Ishan Misra
Piotr Bojanowski
Pascal Vincent
Michael Rabbat
Yann LeCun
Nicolas Ballas
This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations. W… (see more)e introduce the Image-based Joint-Embedding Predictive Architecture (I-JEPA), a non-generative approach for self-supervised learning from images. The idea behind I-JEPA is simple: from a single context block, predict the representations of various target blocks in the same image. A core design choice to guide I-JEPA towards producing semantic representations is the masking strategy; specifically, it is crucial to (a) sample target blocks with sufficiently large scale (semantic), and to (b) use a sufficiently informative (spatially distributed) context block. Empirically, when combined with Vision Transformers, we find I-JEPA to be highly scalable. For instance, we train a ViT-Huge/14 on ImageNet using 16 A100 GPUs in under 72 hours to achieve strong downstream performance across a wide range of tasks, from linear classification to object counting and depth prediction.
2023-06-17
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (published)
doi.org
arxiv.org
Simulated Annealing in Early Layers Leads to Better Generalization
Amir M. Sarfi
Zahra Karimpour
Muawiz Chaudhary
Nasir M. Khalid
Mirco Ravanelli
Sudhir Mudur
Eugene Belilovsky
Recently, a number of iterative learning methods have been introduced to improve generalization. These typically rely on training for longer… (see more) periods of time in exchange for improved generalization. LLF (later-layer-forgetting) is a state-of-the-art method in this category. It strengthens learning in early layers by periodically re-initializing the last few layers of the network. Our principal innovation in this work is to use Simulated annealing in EArly Layers (SEAL) of the network in place of re-initialization of later layers. Essentially, later layers go through the normal gradient descent process, while the early layers go through short stints of gradient ascent followed by gradient descent. Extensive experiments on the popular Tiny-ImageNet dataset benchmark and a series of transfer learning and few-shot learning tasks show that we outperform LLF by a significant margin. We further show that, compared to normal training, LLF features, although improving on the target task, degrade the transfer learning performance across all datasets we explored. In comparison, our method outperforms LLF across the same target datasets by a large margin. We also show that the prediction depth of our method is significantly lower than that of LLF and normal training, indicating on average better prediction performance. 11The code to reproduce our results is publicly available at: https://github.com/amiiir-sarfi/SEAL
2023-06-17
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (published)
doi.org
arxiv.org
A Survey of Contextual Optimization Methods for Decision Making under Uncertainty
Utsav Sadana
Abhilash Reddy Chenreddy
Érick Delage
Alexandre Forel
Emma Frejinger
Thibaut Vidal
2023-06-17
ArXiv (preprint)
doi.org
arxiv.org
DA Wand: Distortion-Aware Selection Using Neural Mesh Parameterization
Richard Liu
Noam Aigerman
Vladimir Kim
Rana Hanocka
We present a neural technique for learning to select a local sub-region around a point which can be used for mesh parameterization. The moti… (see more)vation for our framework is driven by interactive workflows used for decaling, texturing, or painting on surfaces. Our key idea is to incorporate segmentation probabilities as weights of a classical parameterization method, implemented as a novel differentiable parameterization layer within a neural network framework. We train a segmentation network to select 3D regions that are parameterized into 2D and penalized by the resulting distortion, giving rise to segmentations which are distortion-aware. Following training, a user can use our system to interactively select a point on the mesh and obtain a large, meaningful region around the selection which induces a low-distortion parameterization. Our code11https://github.com/threedle/DA-Wand and project22https://threedle.github.io/DA-Wand/ are publicly available.
2023-06-17
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (published)
doi.org
arxiv.org
Empirical Study on Optimizer Selection for Out-of-Distribution Generalization
Hiroki Naganuma
Kartik Ahuja
Shiro Takagi
Tetsuya Motokawa
Rio Yokota
Kohta Ishikawa
Ikuro Sato
Ioannis Mitliagkas
Modern deep learning systems do not generalize well when the test data distribution is slightly different to the training data distribution.… (see more) While much promising work has been accomplished to address this fragility, a systematic study of the role of optimizers and their out-of-distribution generalization performance has not been undertaken. In this study, we examine the performance of popular first-order optimizers for different classes of distributional shift under empirical risk minimization and invariant risk minimization. We address this question for image and text classification using DomainBed, WILDS, and Backgrounds Challenge as testbeds for studying different types of shifts---namely correlation and diversity shift. We search over a wide range of hyperparameters and examine classification accuracy (in-distribution and out-of-distribution) for over 20,000 models. We arrive at the following findings, which we expect to be helpful for practitioners: i) adaptive optimizers (e.g., Adam) perform worse than non-adaptive optimizers (e.g., SGD, momentum SGD) on out-of-distribution performance. In particular, even though there is no significant difference in in-distribution performance, we show a measurable difference in out-of-distribution performance. ii) in-distribution performance and out-of-distribution performance exhibit three types of behavior depending on the dataset---linear returns, increasing returns, and diminishing returns. For example, in the training of natural language data using Adam, fine-tuning the performance of in-distribution performance does not significantly contribute to the out-of-distribution generalization performance.
2023-06-16
TMLR (accepted)
doi.org
openreview.net
Interpretable deep learning architectures for improving drug response prediction performance: myth or reality?
Yihui Li
David Earl Hostallero
Amin Emad
Motivation: Recent advances in deep learning model development have enabled more accurate prediction of drug response in cancer. However, th… (see more)e black-box nature of these models still remains a hurdle in their adoption for precision cancer medicine. Recent efforts have focused on making these models interpretable by incorporating signaling pathway information in model architecture. While these models improve interpretability, it is unclear whether this higher interpretability comes at the cost of less accurate predictions, or a prediction improvement can also be obtained. Results: In this study, we comprehensively and systematically assessed four state-of-the-art interpretable models developed for drug response prediction to answer this question using three pathway collections. Our results showed that models that explicitly incorporate pathway information in the form of a latent layer perform worse compared to models that incorporate this information implicitly. Moreover, in most evaluation setups the best performance is achieved using a simple black-box model. In addition, replacing the signaling pathways with randomly generated pathways shows a comparable performance for the majority of these interpretable models. Our results suggest that new interpretable models are necessary to improve the drug response prediction performance. In addition, the current study provides different baseline models and evaluation setups necessary for such new models to demonstrate their superior prediction performance. Availability and Implementation: Implementation of all methods are provided in https://github.com/Emad-COMBINE-lab/InterpretableAI_for_DRP. Generated uniform datasets are in https://zenodo.org/record/7101665#.YzS79HbMKUk. Contact: amin.emad@mcgill.ca Supplementary Information: Online-only supplementary data is available at the journal’s website.
2023-06-16
Bioinformatics (published)
doi.org
Investigating Prompting Techniques for Zero- and Few-Shot Visual Question Answering
Md. Rabiul Awal
Le Zhang
Aishwarya Agrawal
In this paper, we explore effective prompting techniques to enhance zero- and few-shot Visual Question Answering (VQA) performance in contem… (see more)porary Vision-Language Models (VLMs). Central to our investigation is the role of question templates in guiding VLMs to generate accurate answers. We identify that specific templates significantly influence VQA outcomes, underscoring the need for strategic template selection. Another pivotal aspect of our study is augmenting VLMs with image captions, providing them with additional visual cues alongside direct image features in VQA tasks. Surprisingly, this augmentation significantly improves the VLMs' performance in many cases, even though VLMs"see"the image directly! We explore chain-of-thought (CoT) reasoning and find that while standard CoT reasoning causes drops in performance, advanced methods like self-consistency can help recover it. Furthermore, we find that text-only few-shot examples enhance VLMs' alignment with the task format, particularly benefiting models prone to verbose zero-shot answers. Lastly, to mitigate the challenges associated with evaluating free-form open-ended VQA responses using string-matching based VQA metrics, we introduce a straightforward LLM-guided pre-processing technique to adapt the model responses to the expected ground-truth answer distribution. In summary, our research sheds light on the intricacies of prompting strategies in VLMs for VQA, emphasizing the synergistic use of captions, templates, and pre-processing to enhance model efficacy.
2023-06-16
ArXiv (preprint)
doi.org
arxiv.org
Preventing Dimensional Collapse in Contrastive Local Learning with Subsampling
Louis Fournier
Adeetya Patel
Michael Eickenberg
Edouard Oyallon
Eugene Belilovsky
2023-06-16
ICML.cc/2023/Workshop/LLW (published)
openreview.net
openreview.net
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding
Le Zhang
Rabiul Awal
Aishwarya Agrawal
Vision-Language Models (VLMs), such as CLIP, exhibit strong image-text comprehension abilities, facilitating advances in several downstream … (see more)tasks such as zero-shot image classification, image-text retrieval, and text-to-image generation. However, the compositional reasoning abilities of existing VLMs remains subpar. The root of this limitation lies in the inadequate alignment between the images and captions in the pretraining datasets. Additionally, the current contrastive learning objective fails to focus on fine-grained grounding components like relations, actions, and attributes, resulting in"bag-of-words"representations. We introduce a simple and effective method to improve compositional reasoning in VLMs. Our method better leverages available datasets by refining and expanding the standard image-text contrastive learning framework. Our approach does not require specific annotations and does not incur extra parameters. When integrated with CLIP, our technique yields notable improvement over state-of-the-art baselines across five vision-language compositional benchmarks. We open-source our code at https://github.com/lezhang7/Enhance-FineGrained.
2023-06-15
ArXiv (preprint)
arxiv.org
arxiv.org