Related papers: Inductive Biases for Object-Centric Representation…

Task-driven features learned by modern object detectors optimize end task loss yet often capture shortcut correlations that fail to reflect underlying annotation structure. Such representations limit transfer, interpretability, and…

Learned visual dynamics models have proven effective for robotic manipulation tasks. Yet, it remains unclear how best to represent scenes involving multi-object interactions. Current methods decompose a scene into discrete objects, but they…

Context can strongly affect object representations, sometimes leading to undesired biases, particularly when objects appear in out-of-distribution backgrounds at inference. At the same time, many object-centric tasks require to leverage the…

State-of-the-art methods in generative representation learning yield semantic disentanglement, but typically do not consider physical scene parameters, such as geometry, albedo, lighting, or camera. We posit that inverse rendering, a way to…

It is generally believed that the human visual system is biased towards the recognition of shapes rather than textures. This assumption has led to a growing body of work aiming to align deep models' decision-making processes with the…

Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…

Segmentation of objects in microscopy images is required for many biomedical applications. We introduce object-centric embeddings (OCEs), which embed image patches such that the spatial offsets between patches cropped from the same object…

Creating realistic virtual assets is a time-consuming process: it usually involves an artist designing the object, then spending a lot of effort on tweaking its appearance. Intricate details and certain effects, such as subsurface…

In deformable object manipulation, we often want to interact with specific segments of an object that are only defined in non-deformed models of the object. We thus require a system that can recognize and locate these segments in sensor…

We introduce a new neural architecture and an unsupervised algorithm for learning invariant representations from temporal sequence of images. The system uses two groups of complex cells whose outputs are combined multiplicatively: one that…

Recent literature shows that large-scale language modeling provides excellent reusable sentence representations with both recurrent and self-attentive architectures. However, there has been less clarity on the commonalities and differences…

This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data…

Deep imitation learning is promising for solving dexterous manipulation tasks because it does not require an environment model and pre-programmed robot behavior. However, its application to dual-arm manipulation tasks remains challenging.…

Instance segmentation datasets play a crucial role in training accurate and robust computer vision models. However, obtaining accurate mask annotations to produce high-quality segmentation datasets is a costly and labor-intensive process.…

The human brain represents objects in a way that is both invariant across instances and flexible enough to support different contexts and tasks. Yet it remains unknown how object representations are dynamically remapped as the same object…

Recent advances in Neural Fields mostly rely on developing task-specific supervision which often complicates the models. Rather than developing hard-to-combine and specific modules, another approach generally overlooked is to directly…

Transformer-based detection and segmentation methods use a list of learned detection queries to retrieve information from the transformer network and learn to predict the location and category of one specific object from each query. We…

Most efforts in interpretability in deep learning have focused on (1) extracting explanations of a specific downstream task in relation to the input features and (2) imposing constraints on the model, often at the expense of predictive…

Recently, intermediate feature maps of pre-trained convolutional neural networks have shown significant perceptual quality improvements, when they are used in the loss function for training new networks. It is believed that these features…

Humans rely heavily on shapes as a primary cue for object recognition. As secondary cues, colours and textures are also beneficial in this regard. Convolutional neural networks (CNNs), an imitation of biological neural networks, have been…