Related papers: IntraQ: Learning Synthetic Images with Intra-Class…
Zero-shot learning (ZSL) aims to recognize classes that do not have samples in the training set. One representative solution is to directly learn an embedding function associating visual features with corresponding class semantics for…
Convolutional neural networks are able to learn realistic image priors from numerous training samples in low-level image generation and restoration. We show that, for high-level image recognition tasks, we can further reconstruct…
Quantizing the floating-point weights and activations of deep convolutional neural networks to fixed-point representation yields reduced memory footprints and inference time. Recently, efforts have been afoot towards zero-shot quantization…
We present a network architecture which compares RGB images and untextured 3D models by the similarity of the represented shape. Our system is optimised for zero-shot retrieval, meaning it can recognise shapes never shown in training. We…
Zero-Shot Learning (ZSL) aims to recognize unseen classes by generalizing the knowledge, i.e., visual and semantic relationships, obtained from seen classes, where image augmentation techniques are commonly applied to improve the…
Recently, many zero-shot learning (ZSL) methods focused on learning discriminative object features in an embedding feature space, however, the distributions of the unseen-class features learned by these methods are prone to be partly…
Generative zero-shot learning (ZSL) methods typically synthesize visual features for unseen classes using predefined semantic attributes, followed by training a fully supervised classification model. While effective, these methods require…
Existing quantization aware training methods attempt to compensate for the quantization loss by leveraging on training data, like most of the post-training quantization methods, and are also time consuming. Both these methods are not…
The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during inference. However, since the unseen objects are never…
Discrete image tokenization is a key bottleneck for scalable visual generation: a tokenizer must remain compact for efficient latent-space priors while preserving semantic structure and using discrete capacity effectively. Existing…
Recently, learned image compression methods have been actively studied. Among them, entropy-minimization based approaches have achieved superior results compared to conventional image codecs such as BPG and JPEG2000. However, the quality…
Zero-shot learning (ZSL) which aims to recognize unseen object classes by only training on seen object classes, has increasingly been of great interest in Machine Learning, and has registered with some successes. Most existing ZSL methods…
Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out with the help of mid-level semantic descriptors associated…
Zero-shot learning (ZSL) aims at recognizing classes for which no visual sample is available at training time. To address this issue, one can rely on a semantic description of each class. A typical ZSL model learns a mapping between the…
Zero-shot object detection aims at incorporating class semantic vectors to realize the detection of (both seen and) unseen classes given an unconstrained test image. In this study, we reveal the core challenges in this research area: how to…
Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or…
Model quantization is considered as a promising method to greatly reduce the resource requirements of deep neural networks. To deal with the performance drop induced by quantization errors, a popular method is to use training data to…
The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails to adapt to their varying complexity. Dynamic,…
The recognition of unseen objects from a semantic representation or textual description, usually denoted as zero-shot learning, is more prone to be used in real-world scenarios when compared to traditional object recognition. Nevertheless,…
We present ZeroComp, an effective zero-shot 3D object compositing approach that does not require paired composite-scene images during training. Our method leverages ControlNet to condition from intrinsic images and combines it with a Stable…