Marco Pedersoli

2025-11-10

Proceedings of the Fourth International Conference on Automated Machine Learning (publié)

proceedings.mlr.press

LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups

Masih Aminbeidokhti

Subhankar Roy

Eric Granger

Elisa Ricci

Real-world datasets typically exhibit long-tailed (LT) distributions, where a few head classes dominate and many tail classes are severely u… (voir plus)nderrepresented. While recent work shows that parameter-efficient fine-tuning (PEFT) methods like LoRA and AdaptFormer preserve tail-class performance on foundation models such as CLIP, we find that they do so at the cost of head-class accuracy. We identify the head-tail ratio, the proportion of head to tail classes, as a crucial but overlooked factor influencing this trade-off. Through controlled experiments on CIFAR100 with varying imbalance ratio (

2025-11-10

ArXiv (prépublication)

High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization

Masih Aminbeidokhti

Heitor Rapela Medeiros

Srikanth Muralidharan

Eric Granger

2025-10-07

ArXiv (prépublication)

Revisiting Mixout: An Overlooked Path to Robust Finetuning

Masih Aminbeidokhti

Heitor Rapela Medeiros

Eric Granger

Finetuning vision foundation models often improves in-domain accuracy but comes at the cost of robustness under distribution shift. We revis… (voir plus)it Mixout, a stochastic regularizer that intermittently replaces finetuned weights with their pretrained reference, through the lens of a single-run, weight-sharing implicit ensemble. This perspective reveals three key levers that govern robustness: the \emph{masking anchor}, \emph{resampling frequency}, and \emph{mask sparsity}. Guided by this analysis, we introduce GMixout, which (i) replaces the fixed anchor with an exponential moving-average snapshot that adapts during training, and (ii) regulates masking period via an explicit resampling-frequency hyperparameter. Our sparse-kernel implementation updates only a small fraction of parameters with no inference-time overhead, enabling training on consumer-grade GPUs. Experiments on benchmarks covering covariate shift, corruption, and class imbalance, ImageNet / ImageNet-LT, DomainNet, iWildCam, and CIFAR100-C, GMixout consistently improves in-domain accuracy beyond zero-shot performance while surpassing both Model Soups and strong parameter-efficient finetuning baselines under distribution shift.

2025-10-07

ArXiv (prépublication)

VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors

Atif Belal

Heitor Rapela Medeiros

Eric Granger

2025-09-30

ArXiv (prépublication)

AInstein: Can AI Rediscover Scientific Concepts from First Principles?

Shambhavi Mishra

Gaurav Sahu

Laurent Charlin

Jose Dolz

Christopher Pal

Large language models have demonstrated remarkable capabilities across diverse tasks, yet a fundamental question remains: can these models g… (voir plus)enuinely rediscover complex scientific insights, or do they merely recite memorized information? We present AInstein, a novel framework for evaluating whether language models can derive established scientific concepts from first principles when stripped of domain-specific terminology. Rather than testing the recall of scientific facts, we reformulate landmark discoveries as conceptual puzzles, challenging models to reconstruct the underlying technical solutions independently.

2025-09-21

NeurIPS.cc/2025/Workshop/WiML (publié)

openreview.net

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

Juan A. Rodriguez

Haotian Zhang

Abhay Puri

Aarash Feizi

Rishav Pramanik

Pascal Wichmann

Arnab Mondal

Mohammad Reza Samsami

Sai Rajeswar

Christopher Pal

Scalable Vector Graphics (SVG) offer a powerful format for representing visual designs as interpretable code. Recent advances in vision-lang… (voir plus)uage models (VLMs) have enabled high-quality SVG generation by framing the problem as a code generation task and leveraging large-scale pretraining. VLMs are particularly suitable for this task as they capture both global semantics and fine-grained visual patterns, while transferring knowledge across vision, natural language, and code domains. However, existing VLM approaches often struggle to produce faithful and efficient SVGs because they never observe the rendered images during training. Although differentiable rendering for autoregressive SVG code generation remains unavailable, rendered outputs can still be compared to original inputs, enabling evaluative feedback suitable for reinforcement learning (RL). We introduce RLRF (Reinforcement Learning from Rendering Feedback), an RL method that enhances SVG generation in autoregressive VLMs by leveraging feedback from rendered SVG outputs. Given an input image, the model generates SVG roll-outs that are rendered and compared to the original image to compute a reward. This visual fidelity feedback guides the model toward producing more accurate, efficient, and semantically coherent SVGs. RLRF significantly outperforms supervised fine-tuning, addressing common failure modes and enabling precise, high-quality SVG generation with strong structural understanding and generalization.

2025-09-17

NeurIPS.cc/2025/Conference (poster)

openreview.net

Infrared Object Detection with Ultra Small ConvNets: Is ImageNet Pretraining Still Useful?

Srikanth Muralidharan

Heitor Rapela Medeiros

Masih Aminbeidokhti

Eric Granger

Many real-world applications require recognition models that are robust to different operational conditions and modalities, but at the same … (voir plus)time run on small embedded devices, with limited hardware. While for normal size models, pre-training is known to be very beneficial in accuracy and robustness, for small models, that can be employed for embedded and edge devices, its effect is not clear. In this work, we investigate the effect of ImageNet pretraining on increasingly small backbone architectures (ultra-small models, with

2025-08-03

ArXiv (prépublication)

Low-Rank Expert Merging for Multi-Source Domain Adaptation in Person Re-Identification

Taha Mustapha Nehdi

Nairouz Mrabah

Atif Belal

Eric Granger

2025-07-31

arXiv (publié)

MuSACo: Multimodal Subject-Specific Selection and Adaptation for Expression Recognition with Co-Training

Muhammad Osama Zeeshan

Natacha Gillet

Alessandro Lameiras Koerich

Francois Bremond

Eric Granger

2025-07-31

arXiv (publié)

Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method

Masoumeh Sharafi

Soufiane Belharbi

Houssem Ben Salem

Ali Etemad

Alessandro Lameiras Koerich

Simon Bacon

Eric Granger

Facial expression recognition (FER) models are employed in many video-based affective computing applications, such as human-computer interac… (voir plus)tion and healthcare monitoring. However, deep FER models often struggle with subtle expressions and high inter-subject variability, limiting their performance in real-world applications. To improve their performance, source-free domain adaptation (SFDA) methods have been proposed to personalize a pretrained source model using only unlabeled target domain data, thereby avoiding data privacy, storage, and transmission constraints. This paper addresses a challenging scenario where source data is unavailable for adaptation, and only unlabeled target data consisting solely of neutral expressions is available. SFDA methods are not typically designed to adapt using target data from only a single class. Further, using models to generate facial images with non-neutral expressions can be unstable and computationally intensive. In this paper, personalized feature translation (PFT) is proposed for SFDA. Unlike current image translation methods for SFDA, our lightweight method operates in the latent space. We first pre-train the translator on the source domain data to transform the subject-specific style features from one source subject into another. Expression information is preserved by optimizing a combination of expression consistency and style-aware objectives. Then, the translator is adapted on neutral target data, without using source data or image synthesis. By translating in the latent space, PFT avoids the complexity and noise of face expression generation, producing discriminative embeddings optimized for classification. Using PFT eliminates the need for image synthesis, reduces computational overhead (using a lightweight translator), and only adapts part of the model, making the method efficient compared to image-based translation.

2025-07-31

arXiv (publié)

WiSE-OD: Benchmarking Robustness in Infrared Object Detection

Heitor Rapela Medeiros

Atif Belal

Masih Aminbeidokhti

Eric Granger

2025-06-30

arXiv (publié)