Aritra Bhowmik

Elia Peruzzo, Aritra Bhowmik, Guillaume Sautiere et al.

Autoregressive (AR) image generation models are highly expressive but computationally intensive, motivating effective model compression. Knowledge distillation (KD) is a natural approach for model compression and has been widely studied in language modeling, yet its behavior in visual AR generation remains underexplored. In this work, we present the first systematic study of distillation strategies for AR image models. Our analysis shows that while standard distillation can yield meaningful gains, recent methods developed for language do not directly transfer to images: long decoding horizons and visual token ambiguity make teacher supervision unreliable especially under student-conditioned contexts. To address this, we propose VarKD, a distillation framework for visual autoregressive models that distills on student samples while selectively applying teacher supervision and reducing token-level ambiguity. Experiments on ImageNet across multiple AR backbones show that VarKD consistently outperforms prior distillation baselines, narrowing the gap to large-scale models.

Aritra Bhowmik, Yu Wang, Nora Baka et al.

The goal of this paper is to detect objects by exploiting their interrelationships. Contrary to existing methods, which learn objects and relations separately, our key idea is to learn the object-relation distribution jointly. We first propose a novel way of creating a graphical representation of an image from inter-object relation priors and initial class predictions, we call a context-likelihood graph. We then learn the joint distribution with an energy-based modeling technique which allows to sample and refine the context-likelihood graph iteratively for a given image. Our formulation of jointly learning the distribution enables us to generate a more accurate graph representation of an image which leads to a better object detection performance. We demonstrate the benefits of our context-likelihood graph formulation and the energy-based graph refinement via experiments on the Visual Genome and MS-COCO datasets where we achieve a consistent improvement over object detectors like DETR and Faster-RCNN, as well as alternative methods modeling object interrelationships separately. Our method is detector agnostic, end-to-end trainable, and especially beneficial for rare object classes.

Aritra Bhowmik, Pascal Mettes, Martin R. Oswald et al.

This paper revisits the problem of predicting box locations in object detection architectures. Typically, each box proposal or box query aims to directly maximize the intersection-over-union score with the ground truth, followed by a winner-takes-all non-maximum suppression where only the highest scoring box in each region is retained. We observe that both steps are sub-optimal: the first involves regressing proposals to the entire ground truth, which is a difficult task even with large receptive fields, and the second neglects valuable information from boxes other than the top candidate. Instead of regressing proposals to the whole ground truth, we propose a simpler approach: regress only to the area of intersection between the proposal and the ground truth. This avoids the need for proposals to extrapolate beyond their visual scope, improving localization accuracy. Rather than adopting a winner-takes-all strategy, we take the union over the regressed intersections of all boxes in a region to generate the final box outputs. Our plug-and-play method integrates seamlessly into proposal-based, grid-based, and query-based detection architectures with minimal modifications, consistently improving object localization and instance segmentation. We demonstrate its broad applicability and versatility across various detection and segmentation tasks.

Agata Żywot, Iason Skylitsis, Thijmen Nijdam et al.

Text-to-image diffusion models like Stable Diffusion generate high-quality images from text, but lack a way to inject visual guidance (e.g. sketches, styles) at inference without retraining. Existing methods either require computationally expensive fine-tuning or rely on style transfer techniques that risk semantic misalignment with textual prompts. We introduce Visual Concept Fusion (VCF), the first method offering dual conditioning on both an image and text prompt at inference time without any concept-specific training. VCF enables visual concept injection into Stable Diffusion by aligning CLIP image features with the text embedding space. VCF consists of three components: (1) a lightweight aligner that maps image tokens to the text embedding manifold using InfoNCE and cross-attention reconstruction losses, (2) a fusion strategy that preserves both textual and visual semantics, and (3) an optional Prompt-Noise Optimization (PNO) module for test-time refinement. Our experiments demonstrate that VCF successfully transfers visual attributes including style, composition, and color palette from reference images while maintaining prompt adherence. Quantitative results show a trade-off between text alignment (CLIP score) and visual correspondence (LPIPS), with VCF outperforming baselines in reference fidelity.

Aritra Bhowmik, Denis Korzhenkov, Cees G. M. Snoek et al.

Text-to-video diffusion models have enabled high-quality video synthesis, yet often fail to generate temporally coherent and physically plausible motion. A key reason is the models' insufficient understanding of complex motions that natural videos often entail. Recent works tackle this problem by aligning diffusion model features with those from pretrained video encoders. However, these encoders mix video appearance and dynamics into entangled features, limiting the benefit of such alignment. In this paper, we propose a motion-centric alignment framework that learns a disentangled motion subspace from a pretrained video encoder. This subspace is optimized to predict ground-truth optical flow, ensuring it captures true motion dynamics. We then align the latent features of a text-to-video diffusion model to this new subspace, enabling the generative model to internalize motion knowledge and generate more plausible videos. Our method improves the physical commonsense in a state-of-the-art video diffusion model, while preserving adherence to textual prompts, as evidenced by empirical evaluations on VideoPhy, VideoPhy2, VBench, and VBench-2.0, along with a user study.

Aritra Bhowmik, Fida Mohammad Thoker, Carlos Hinojosa et al.

Masked modeling has emerged as a powerful self-supervised learning framework, but existing methods largely rely on random masking, disregarding the structural properties of different modalities. In this work, we introduce structured noise-based masking, a simple yet effective approach that naturally aligns with the spatial, temporal, and spectral characteristics of video and audio data. By filtering white noise into distinct color noise distributions, we generate structured masks that preserve modality-specific patterns without requiring handcrafted heuristics or access to the data. Our approach improves the performance of masked video and audio modeling frameworks without any computational overhead. Extensive experiments demonstrate that structured noise masking achieves consistent improvement over random masking for standard and advanced masked modeling methods, highlighting the importance of modality-aware masking strategies for representation learning.

Aritra Bhowmik, Mohammad Mahdi Derakhshani, Dennis Koelma et al.

Spatial awareness is key to enable embodied multimodal AI systems. Yet, without vast amounts of spatial supervision, current Multimodal Large Language Models (MLLMs) struggle at this task. In this paper, we introduce TWIST & SCOUT, a framework that equips pre-trained MLLMs with visual grounding ability without forgetting their existing image and language understanding skills. To this end, we propose TWIST, a twin-expert stepwise tuning module that modifies the decoder of the language model using one frozen module pre-trained on image understanding tasks and another learnable one for visual grounding tasks. This allows the MLLM to retain previously learned knowledge and skills, while acquiring what is missing. To fine-tune the model effectively, we generate a high-quality synthetic dataset we call SCOUT, which mimics human reasoning in visual grounding. This dataset provides rich supervision signals, describing a step-by-step multimodal reasoning process, thereby simplifying the task of visual grounding. We evaluate our approach on several standard benchmark datasets, encompassing grounded image captioning, zero-shot localization, and visual grounding tasks. Our method consistently delivers strong performance across all tasks, while retaining the pre-trained image understanding capabilities.

Aritra Bhowmik, Stefan Gumhold, Carsten Rother et al.

We address a core problem of computer vision: Detection and description of 2D feature points for image matching. For a long time, hand-crafted designs, like the seminal SIFT algorithm, were unsurpassed in accuracy and efficiency. Recently, learned feature detectors emerged that implement detection and description using neural networks. Training these networks usually resorts to optimizing low-level matching scores, often pre-defining sets of image patches which should or should not match, or which should or should not contain key points. Unfortunately, increased accuracy for these low-level matching scores does not necessarily translate to better performance in high-level vision tasks. We propose a new training methodology which embeds the feature detector in a complete vision pipeline, and where the learnable parameters are trained in an end-to-end fashion. We overcome the discrete nature of key point selection and descriptor matching using principles from reinforcement learning. As an example, we address the task of relative pose estimation between a pair of images. We demonstrate that the accuracy of a state-of-the-art learning-based feature detector can be increased when trained for the task it is supposed to solve at test time. Our training methodology poses little restrictions on the task to learn, and works for any architecture which predicts key point heat maps, and descriptors for key point locations.