Most of the existing algorithms for zero-shot classification problems typically rely on the attribute-based semantic relations among categories to realize the classification of novel categories without observing any of their instances. However, training the zero-shot classification models still requires attribute labeling for each class (or even instance) in the training dataset, which is also expensive. To this end, in this paper, we bring up a new problem scenario: ''Can we derive zero-shot learning for novel attribute detectors/classifiers and use them to automatically annotate the dataset for labeling efficiency?'' Basically, given only a small set of detectors that are learned to recognize some manually annotated attributes (i.e., the seen attributes), we aim to synthesize the detectors of novel attributes in a zero-shot learning manner. Our proposed method, Zero-Shot Learning for Attributes (ZSLA), which is the first of its kind to the best of our knowledge, tackles this new research problem by applying the set operations to first decompose the seen attributes into their basic attributes and then recombine these basic attributes into the novel ones. Extensive experiments are conducted to verify the capacity of our synthesized detectors for accurately capturing the semantics of the novel attributes and show their superior performance in terms of detection and localization compared to other baseline approaches. Moreover, we demonstrate the application of automatic annotation using our synthesized detectors on Caltech-UCSD Birds-200-2011 dataset. Various generalized zero-shot classification algorithms trained upon the dataset re-annotated by ZSLA shows comparable performance with those trained with the manual ground-truth annotations.

Knowledge distillation (KD) is a general neural network training approach that uses a teacher model to guide the student model. Existing works mainly study KD from the network output side (e.g., trying to design a better KD loss function), while few have attempted to understand it from the input side. Especially, its interplay with data augmentation (DA) has not been well understood. In this paper, we ask: Why do some DA schemes (e.g., CutMix) inherently perform much better than others in KD? What makes a "good" DA in KD? Our investigation from a statistical perspective suggests that a good DA scheme should reduce the covariance of the teacher-student cross-entropy.

Recently, Wong et al. (2020) showed that adversarial training with single-step FGSM leads to a characteristic failure mode named catastrophic overfitting (CO), in which a model becomes suddenly vulnerable to multi-step attacks. Experimentally they showed that simply adding a random perturbation prior to FGSM (RS-FGSM) could prevent CO. However, Andriushchenko & Flammarion (2020) observed that RS-FGSM still leads to CO for larger perturbations, and proposed a computationally expensive regularizer (GradAlign) to avoid it. In this work, we methodically revisit the role of noise and clipping in single-step adversarial training. Contrary to previous intuitions, we find that using a stronger noise around the clean sample combined with \textit{not clipping} is highly effective in avoiding CO for large perturbation radii. We then propose Noise-FGSM (N-FGSM) that, while providing the benefits of single-step adversarial training, does not suffer from CO. Empirical analyses on a large suite of experiments show that N-FGSM is able to match or surpass the performance of previous state of-the-art GradAlign while achieving 3$\times$ speed-up.

Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning. Despite its success, the influence of different view choices has been less studied. In this paper, we use theoretical and empirical analysis to better understand the importance of view selection, and argue that we should reduce the mutual information (MI) between views while keeping task-relevant information intact. To verify this hypothesis, we devise unsupervised and semi-supervised frameworks that learn effective views by aiming to reduce their MI. We also consider data augmentation as a way to reduce MI, and show that increasing data augmentation indeed leads to decreasing MI and improves downstream classification accuracy. As a by-product, we achieve a new state-of-the-art accuracy on unsupervised pre-training for ImageNet classification (73% top-1 linear readout with a ResNet-50).

We present DreamWaltz, a novel framework for generating and animating complex 3D avatars given text guidance and parametric human body prior. While recent methods have shown encouraging results for text-to-3D generation of common objects, creating high-quality and animatable 3D avatars remains challenging. To create high-quality 3D avatars, DreamWaltz proposes 3D-consistent occlusion-aware Score Distillation Sampling (SDS) to optimize implicit neural representations with canonical poses. It provides view-aligned supervision via 3D-aware skeleton conditioning which enables complex avatar generation without artifacts and multiple faces. For animation, our method learns an animatable 3D avatar representation from abundant image priors of diffusion model conditioned on various poses, which could animate complex non-rigged avatars given arbitrary poses without retraining. Extensive evaluations demonstrate that DreamWaltz is an effective and robust approach for creating 3D avatars that can take on complex shapes and appearances as well as novel poses for animation. The proposed framework further enables the creation of complex scenes with diverse compositions, including avatar-avatar, avatar-object and avatar-scene interactions.

Stop Trying To Make A.I. Trendy From vandalized subway ads to bespoke caps, A.I. startups are flooding traditional marketing spaces and getting backlash for it. Please enable javascript to get your Slate Plus feeds. If you can't access your feeds, please contact customer support. Check your phone for a link to finish setting up your feed. Please enter a valid phone number.

Perplexity's AI-powered browser, Comet, contained a dangerous vulnerability, according to an Israeli cybersecurity firm. Perplexity's AI-powered browser, Comet, contained a dangerous vulnerability, according to an Israeli cybersecurity firm. Welcome back to, TIME's new twice-weekly newsletter about AI. If you're reading this in your browser, why not subscribe to have the next one delivered straight to your inbox? Last week, Perplexity announced that its AI-powered browser, called Comet, would be made free for all users after previously requiring a paid subscription.

This work studies convergence rates of the gradients for convex composite objectives by combining Nesterov's tricks used for gradient descent with SGD. The authors provide three approaches which differ from each other only slightly and they provide the convergence rates for all the proposed approaches. My comments on this work are as follow: 1. It is indeed important to study convergence rates of gradients especially for non-convex problems. The authors motivate the readers by mentioning this but they assume convexity in their problem set-up.

Artificial Intelligence (AI) is fast becoming a mainstay in our business operations. In fact, according to IDC, over the next three years, governments and businesses around the world will invest more than AU$723 billion in AI. Meanwhile, AI technology is projected to be integrated into 90% of the most cutting-edge enterprise applications by 2025. Already, it's beginning to transform everyday life. While it's undoubtedly an exciting time to be alive with all these technological advancements, it's vital to keep a pulse on the human component of technology, ensuring everyone benefits.

Copy AI is an AI-driven copywriting solution that helps businesses generate high-quality content quickly and at scale. It uses natural language processing (NLP) and machine learning (ML) algorithms to automatically generate persuasive copy that is tailored to specific audiences. This AI-powered writing assistant is designed to help marketers, copywriters, and content creators generate more effective and engaging content faster, with minimal effort and cost. Copy AI is an AI-powered copywriting solution that helps businesses generate high-quality content quickly and at scale. It uses natural language processing (NLP) and machine learning (ML) algorithms to automatically generate persuasive copy that is tailored to specific audiences. This AI-powered writing assistant is designed to help marketers, copywriters, and content creators generate more effective and engaging content faster, with minimal effort and cost.