Related papers: Accurate Deep Representation Quantization with Gra…
Recent years have witnessed rapid advances in graph representation learning, with the continuous embedding approach emerging as the dominant paradigm. However, such methods encounter issues regarding parameter efficiency, interpretability,…
A common issue of deep neural networks-based methods for the problem of Single Image Super-Resolution (SISR), is the recovery of finer texture details when super-resolving at large upscaling factors. This issue is particularly related to…
Weight quantization is an effective technique to compress deep neural networks for their deployment on edge devices with limited resources. Traditional loss-aware quantization methods commonly use the quantized gradient to replace the…
Deep hashing models have been proposed as an efficient method for large-scale similarity search. However, most existing deep hashing methods only utilize fine-level labels for training while ignoring the natural semantic hierarchy…
While 3D Gaussian Splatting enables high-quality real-time rendering, existing Gaussian-based frameworks for 3D semantic segmentation still face significant challenges in boundary recognition accuracy. To address this, we propose a novel…
Recent work in Deep Learning has re-imagined the representation of data as functions mapping from a coordinate space to an underlying continuous signal. When such functions are approximated by neural networks this introduces a compelling…
Deep generative modeling has led to new and state of the art approaches for enforcing structural priors in a variety of inverse problems. In contrast to priors given by sparsity, deep models can provide direct low-dimensional…
Self-supervised learning (SSL) has become prevalent for learning representations in computer vision. Notably, SSL exploits contrastive learning to encourage visual representations to be invariant under various image transformations. The…
Our proposed deeply-supervised nets (DSN) method simultaneously minimizes classification error while making the learning process of hidden layers direct and transparent. We make an attempt to boost the classification performance by studying…
We employ a toolset -- dubbed Dr. Frankenstein -- to analyse the similarity of representations in deep neural networks. With this toolset, we aim to match the activations on given layers of two trained neural networks by joining them with a…
Self-Supervised Learning (SSL) has been shown to learn useful and information-preserving representations. Neural Networks (NNs) are widely applied, yet their weight space is still not fully understood. Therefore, we propose to use SSL to…
Recent algorithms for image manipulation detection almost exclusively use deep network models. These approaches require either dense pixelwise groundtruth masks, camera ids, or image metadata to train the networks. On one hand, constructing…
Locating discriminative parts plays a key role in fine-grained visual classification due to the high similarities between different objects. Recent works based on convolutional neural networks utilize the feature maps taken from the last…
We present backpropagation clipping, a novel variant of differentially private stochastic gradient descent (DP-SGD) for privacy-preserving deep learning. Our approach clips each trainable layer's inputs (during the forward pass) and its…
Prediction is a fundamental capability of all living organisms, and has been proposed as an objective for learning sensory representations. Recent work demonstrates that in primate visual systems, prediction is facilitated by neural…
Deep Convolutional Neural Networks (CNN) enforces supervised information only at the output layer, and hidden layers are trained by back propagating the prediction error from the output layer without explicit supervision. We propose a…
Deep learning models are increasingly popular in many machine learning applications where the training data may contain sensitive information. To provide formal and rigorous privacy guarantee, many learning systems now incorporate…
Self-supervised representation learning is a fundamental problem in computer vision with many useful applications (e.g., image search, instance level recognition, copy detection). In this paper we present a new contrastive self-supervised…
Visual place retrieval aims to search images in the database that depict similar places as the query image. However, global descriptors encoded by the network usually fall into a low dimensional principal space, which is harmful to the…
Self-supervised learning provides a promising path towards eliminating the need for costly label information in representation learning on graphs. However, to achieve state-of-the-art performance, methods often need large numbers of…