相关论文: CoReS: Compatible Representations via Stationarity

Neural networks are widely used as a model for classification in a large variety of tasks. Typically, a learnable transformation (i.e. the classifier) is placed at the end of such models returning a value for each class used for…

Continual learning requires models to adapt to new data while preserving previously acquired knowledge. At its core, this challenge can be viewed as principled one-step adaptation: incorporating new information with minimal interference to…

Ensembles of Convolutional neural networks have shown remarkable results in learning discriminative semantic features for image classification tasks. Though, the models in the ensemble often concentrate on similar regions in images. This…

Hierarchies allow feature sharing between objects at multiple levels of representation, can code exponential variability in a very compact way and enable fast inference. This makes them potentially suitable for learning and recognizing a…

Designing agent that can autonomously discover and learn a diversity of structures and skills in unknown changing environments is key for lifelong machine learning. A central challenge is how to learn incrementally representations in order…

Recent studies have made notable progress in video representation learning by transferring image-pretrained models to video tasks, typically with complex temporal modules and video fine-tuning. However, fine-tuning heavy modules may…

Learning effective representations of urban environments requires capturing spatial structure beyond fixed administrative boundaries. Existing geospatial representation learning approaches typically aggregate Points of Interest(POI) into…

The objective of this work is set-based verification, e.g. to decide if two sets of images of a face are of the same person or not. The traditional approach to this problem is to learn to generate a feature vector per image, aggregate them…

Learning self-supervised representations using reconstruction or contrastive losses improves performance and sample complexity of image-based and multimodal reinforcement learning (RL). Here, different self-supervised loss functions have…

Contrastively trained vision-language models have achieved remarkable progress in vision and language representation learning, leading to state-of-the-art models for various downstream multimodal tasks. However, recent research has…

In image retrieval, deep local features learned in a data-driven manner have been demonstrated effective to improve retrieval performance. To realize efficient retrieval on large image database, some approaches quantize deep local features…

Robust long-term visual localization in complex industrial environments is critical for mobile robotic systems. Existing approaches face limitations: handcrafted features are illumination-sensitive, learned features are computationally…

One of the key limitations of modern deep learning approaches lies in the amount of data required to train them. Humans, by contrast, can learn to recognize novel categories from just a few examples. Instrumental to this rapid learning…

Learning a better representation with neural networks is a challenging problem, which was tackled extensively from different prospectives in the past few years. In this work, we focus on learning a representation that could be used for a…

Many learning problems require predicting sets of objects when the number of objects is not known beforehand. Examples include object detection, molecular modeling, and scientific inference tasks such as astrophysical source detection.…

Reaction condition recommendation sits immediately after retrosynthetic disconnection selection, and in practice, chemists require both accurate predictions and the precedents that justify them. We present HiRes (Hierarchical Reaction…

This paper presents Contrastive Reconstruction, ConRec - a self-supervised learning algorithm that obtains image representations by jointly optimizing a contrastive and a self-reconstruction loss. We showcase that state-of-the-art…

This paper proposes inverse feature learning as a novel supervised feature learning technique that learns a set of high-level features for classification based on an error representation approach. The key contribution of this method is to…

We propose a novel biologically-plausible solution to the credit assignment problem motivated by observations in the ventral visual pathway and trained deep neural networks. In both, representations of objects in the same category become…

Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This…