Yen-Chang Hsu

James Seale Smith, Yen-Chang Hsu, Lingyu Zhang et al.

Recent works demonstrate a remarkable ability to customize text-to-image diffusion models while only providing a few example images. What happens if you try to customize such models using multiple, fine-grained concepts in a sequential (i.e., continual) manner? In our work, we show that recent state-of-the-art customization of text-to-image models suffer from catastrophic forgetting when new concepts arrive sequentially. Specifically, when adding a new concept, the ability to generate high quality images of past, similar concepts degrade. To circumvent this forgetting, we propose a new method, C-LoRA, composed of a continually self-regularized low-rank adaptation in cross attention layers of the popular Stable Diffusion model. Furthermore, we use customization prompts which do not include the word of the customized object (i.e., "person" for a human face dataset) and are initialized as completely random embeddings. Importantly, our method induces only marginal additional parameter costs and requires no storage of user data for replay. We show that C-LoRA not only outperforms several baselines for our proposed setting of text-to-image continual customization, which we refer to as Continual Diffusion, but that we achieve a new state-of-the-art in the well-established rehearsal-free continual learning setting for image classification. The high achieving performance of C-LoRA in two separate domains positions it as a compelling solution for a wide range of applications, and we believe it has significant potential for practical impact. Project page: https://jamessealesmith.github.io/continual-diffusion/

Yen-Chang Hsu, Ting Hua, Sungen Chang et al.

Factorizing a large matrix into small matrices is a popular strategy for model compression. Singular value decomposition (SVD) plays a vital role in this compression strategy, approximating a learned matrix with fewer parameters. However, SVD minimizes the squared error toward reconstructing the original matrix without gauging the importance of the parameters, potentially giving a larger reconstruction error for those who affect the task accuracy more. In other words, the optimization objective of SVD is not aligned with the trained model's task accuracy. We analyze this previously unexplored problem, make observations, and address it by introducing Fisher information to weigh the importance of parameters affecting the model prediction. This idea leads to our method: Fisher-Weighted SVD (FWSVD). Although the factorized matrices from our approach do not result in smaller reconstruction errors, we find that our resulting task accuracy is much closer to the original model's performance. We perform analysis with the transformer-based language models, showing our weighted SVD largely alleviates the mismatched optimization objectives and can maintain model performance with a higher compression rate. Our method can directly compress a task-specific model while achieving better performance than other compact model strategies requiring expensive model pre-training. Moreover, the evaluation of compressing an already compact model shows our method can further reduce 9% to 30% parameters with an insignificant impact on task accuracy.

Yen-Chang Hsu, James Smith, Yilin Shen et al.

Knowledge distillation (KD) is a substantial strategy for transferring learned knowledge from one neural network model to another. A vast number of methods have been developed for this strategy. While most method designs a more efficient way to facilitate knowledge transfer, less attention has been put on comparing the effect of knowledge sources such as features, logits, and gradients. This work provides a new perspective to motivate a set of knowledge distillation strategies by approximating the classical KL-divergence criteria with different knowledge sources, making a systematic comparison possible in model compression and incremental learning. Our analysis indicates that logits are generally a more efficient knowledge source and suggests that having sufficient feature dimensions is crucial for the model design, providing a practical guideline for effective KD-based transfer learning.

Ting Hua, Yen-Chang Hsu, Felicity Wang et al.

Singular value decomposition (SVD) is one of the most popular compression methods that approximate a target matrix with smaller matrices. However, standard SVD treats the parameters within the matrix with equal importance, which is a simple but unrealistic assumption. The parameters of a trained neural network model may affect task performance unevenly, which suggests non-equal importance among the parameters. Compared to SVD, the decomposition method aware of parameter importance is the more practical choice in real cases. Unlike standard SVD, weighted value decomposition is a non-convex optimization problem that lacks a closed-form solution. We systematically investigated multiple optimization strategies to tackle the problem and examined our method by compressing Transformer-based language models. Further, we designed a metric to predict when the SVD may introduce a significant performance drop, for which our method can be a rescue strategy. The extensive evaluations demonstrate that our method can perform better than current SOTA methods in compressing Transformer-based language models.

James Seale Smith, Yen-Chang Hsu, Zsolt Kira et al.

Recent work has demonstrated a remarkable ability to customize text-to-image diffusion models to multiple, fine-grained concepts in a sequential (i.e., continual) manner while only providing a few example images for each concept. This setting is known as continual diffusion. Here, we ask the question: Can we scale these methods to longer concept sequences without forgetting? Although prior work mitigates the forgetting of previously learned concepts, we show that its capacity to learn new tasks reaches saturation over longer sequences. We address this challenge by introducing a novel method, STack-And-Mask INcremental Adapters (STAMINA), which is composed of low-ranked attention-masked adapters and customized MLP tokens. STAMINA is designed to enhance the robust fine-tuning properties of LoRA for sequential concept learning via learnable hard-attention masks parameterized with low rank MLPs, enabling precise, scalable learning via sparse adaptation. Notably, all introduced trainable parameters can be folded back into the model after training, inducing no additional inference parameter costs. We show that STAMINA outperforms the prior SOTA for the setting of text-to-image continual customization on a 50-concept benchmark composed of landmarks and human faces, with no stored replay data. Additionally, we extended our method to the setting of continual learning for image classification, demonstrating that our gains also translate to state-of-the-art performance in this standard benchmark.

Chi-Heng Lin, Shangqian Gao, James Seale Smith et al.

Large Language Models (LLMs) have reshaped the landscape of artificial intelligence by demonstrating exceptional performance across various tasks. However, substantial computational requirements make their deployment challenging on devices with limited resources. Recently, compression methods using low-rank matrix techniques have shown promise, yet these often lead to degraded accuracy or introduce significant overhead in parameters and inference latency. This paper introduces \textbf{Mo}dular \textbf{De}composition (MoDeGPT), a novel structured compression framework that does not need recovery fine-tuning while resolving the above drawbacks. MoDeGPT partitions the Transformer block into modules comprised of matrix pairs and reduces the hidden dimensions via reconstructing the module-level outputs. MoDeGPT is developed based on a theoretical framework that utilizes three well-established matrix decomposition algorithms -- Nyström approximation, CR decomposition, and SVD -- and applies them to our redefined transformer modules. Our comprehensive experiments show MoDeGPT, without backward propagation, matches or surpasses previous structured compression methods that rely on gradient information, and saves 98% of compute costs on compressing a 13B model. On \textsc{Llama}-2/3 and OPT models, MoDeGPT maintains 90-95% zero-shot performance with 25-30% compression rates. Moreover, the compression can be done on a single GPU within a few hours and increases the inference throughput by up to 46%.

Shikhar Tuli, James Seale Smith, Haris Jeelani et al.

Large language models (LLMs) have significantly advanced generative applications in natural language processing (NLP). Recent trends in model architectures revolve around efficient variants of transformers or state-space/gated-recurrent models (SSMs, GRMs). However, prevailing SSM/GRM-based methods often emulate only a single attention head, potentially limiting their expressiveness. In this work, we propose MossNet, a novel mixture-of-state-space-experts architecture that emulates a linear multi-head attention (MHA). MossNet leverages a mixture-of-experts (MoE) implementation not only in channel-mixing multi-layered perceptron (MLP) blocks but also in the time-mixing SSM kernels to realize multiple "attention heads." Extensive experiments on language modeling and downstream evaluations show that MossNet outperforms both transformer- and SSM-based architectures of similar model size and data budgets. Larger variants of MossNet, trained on trillions of tokens, further confirm its scalability and superior performance. In addition, real-device profiling on a Samsung Galaxy S24 Ultra and an Nvidia A100 GPU demonstrate favorable runtime speed and resource usage compared to similarly sized baselines. Our results suggest that MossNet is a compelling new direction for efficient, high-performing recurrent LLM architectures.

Junjiao Tian, Dylan Yung, Yen-Chang Hsu et al.

It is well known that vision classification models suffer from poor calibration in the face of data distribution shifts. In this paper, we take a geometric approach to this problem. We propose Geometric Sensitivity Decomposition (GSD) which decomposes the norm of a sample feature embedding and the angular similarity to a target classifier into an instance-dependent and an instance-independent component. The instance-dependent component captures the sensitive information about changes in the input while the instance-independent component represents the insensitive information serving solely to minimize the loss on the training dataset. Inspired by the decomposition, we analytically derive a simple extension to current softmax-linear models, which learns to disentangle the two components during training. On several common vision models, the disentangled model outperforms other calibration methods on standard calibration metrics in the face of out-of-distribution (OOD) data and corruption with significantly less complexity. Specifically, we surpass the current state of the art by 30.8% relative improvement on corrupted CIFAR100 in Expected Calibration Error. Code available at https://github.com/GT-RIPL/Geometric-Sensitivity-Decomposition.git.

Junjiao Tian, Yen-Cheng Liu, Nathan Glaser et al.

Neural Networks can perform poorly when the training label distribution is heavily imbalanced, as well as when the testing data differs from the training distribution. In order to deal with shift in the testing label distribution, which imbalance causes, we motivate the problem from the perspective of an optimal Bayes classifier and derive a post-training prior rebalancing technique that can be solved through a KL-divergence based optimization. This method allows a flexible post-training hyper-parameter to be efficiently tuned on a validation set and effectively modify the classifier margin to deal with this imbalance. We further combine this method with existing likelihood shift methods, re-interpreting them from the same Bayesian perspective, and demonstrating that our method can deal with both problems in a unified way. The resulting algorithm can be conveniently used on probabilistic classification problems agnostic to underlying architectures. Our results on six different datasets and five different architectures show state of art accuracy, including on large-scale imbalanced datasets such as iNaturalist for classification and Synthia for semantic segmentation. Please see https://github.com/GT-RIPL/UNO-IC.git for implementation.

Yen-Chang Hsu, Yen-Cheng Liu, Anita Ramasamy et al.

Continual learning has received a great deal of attention recently with several approaches being proposed. However, evaluations involve a diverse set of scenarios making meaningful comparison difficult. This work provides a systematic categorization of the scenarios and evaluates them within a consistent framework including strong baselines and state-of-the-art methods. The results provide an understanding of the relative difficulty of the scenarios and that simple baselines (Adagrad, L2 regularization, and naive rehearsal strategies) can surprisingly achieve similar performance to current mainstream methods. We conclude with several suggestions for creating harder evaluation scenarios and future research directions. The code is available at https://github.com/GT-RIPL/Continual-Learning-Benchmark

Shangqian Gao, Chi-Heng Lin, Ting Hua et al.

Large Language Models (LLMs) have achieved remarkable success in various natural language processing tasks, including language modeling, understanding, and generation. However, the increased memory and computational costs associated with these models pose significant challenges for deployment on resource-limited devices. Structural pruning has emerged as a promising solution to reduce the costs of LLMs without requiring post-processing steps. Prior structural pruning methods either follow the dependence of structures at the cost of limiting flexibility, or introduce non-trivial additional parameters by incorporating different projection matrices. In this work, we propose a novel approach that relaxes the constraint imposed by regular structural pruning methods and eliminates the structural dependence along the embedding dimension. Our dimension-independent structural pruning method offers several benefits. Firstly, our method enables different blocks to utilize different subsets of the feature maps. Secondly, by removing structural dependence, we facilitate each block to possess varying widths along its input and output dimensions, thereby significantly enhancing the flexibility of structural pruning. We evaluate our method on various LLMs, including OPT, LLaMA, LLaMA-2, Phi-1.5, and Phi-2. Experimental results demonstrate that our approach outperforms other state-of-the-art methods, showing for the first time that structural pruning can achieve an accuracy similar to semi-structural pruning.

I-Chun Chen, Hsu-Shen Liu, Wei-Fang Sun et al. · utoronto

Sparse Mixture-of-Experts (SMoE) models represent a significant advancement in large language model (LLM) development through their efficient parameter utilization. These models achieve substantial performance improvements at reduced inference costs. However, the deployment of SMoE models faces constraints from extensive memory requirements of expert components in resource-limited environments. To address these limitations, this paper introduces Hierarchical Clustering for Sparsely activated Mixture of Experts (HC-SMoE), a task-agnostic expert merging framework for parameter reduction without retraining. HC-SMoE introduces a novel hierarchical clustering approach based on expert outputs to ensure merging robustness independent of routing decisions. The proposed output-based clustering method enables effective capture of functional relationships between experts for large-scale architectures. We provide theoretical analysis and comprehensive evaluations across multiple zero-shot language tasks to demonstrate HC-SMoE's effectiveness in state-of-the-art models including Qwen and Mixtral. The experimental results validate HC-SMoE's superior performance and practical applicability for real-world deployments.

Shikhar Tuli, Chi-Heng Lin, Yen-Chang Hsu et al.

Traditional language models operate autoregressively, i.e., they predict one token at a time. Rapid explosion in model sizes has resulted in high inference times. In this work, we propose DynaMo, a suite of multi-token prediction language models that reduce net inference times. Our models $\textit{dynamically}$ predict multiple tokens based on their confidence in the predicted joint probability distribution. We propose a lightweight technique to train these models, leveraging the weights of traditional autoregressive counterparts. Moreover, we propose novel ways to enhance the estimated joint probability to improve text generation quality, namely co-occurrence weighted masking and adaptive thresholding. We also propose systematic qualitative and quantitative methods to rigorously test the quality of generated text for non-autoregressive generation. One of the models in our suite, DynaMo-7.3B-T3, achieves same-quality generated text as the baseline (Pythia-6.9B) while achieving 2.57$\times$ speed-up with only 5.87% and 2.67% parameter and training time overheads, respectively.

Shangqian Gao, Ting Hua, Reza Shirkavand et al.

Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of complex tasks. However, their huge computational and memory costs raise significant challenges in deploying these models on resource-constrained devices or efficiently serving them. Prior approaches have attempted to alleviate these problems by permanently removing less important model structures, yet these methods often result in substantial performance degradation due to the permanent deletion of model parameters. In this work, we tried to mitigate this issue by reducing the number of active parameters without permanently removing them. Specifically, we introduce a differentiable dynamic pruning method that pushes dense models to maintain a fixed number of active parameters by converting their MLP layers into a Mixture of Experts (MoE) architecture. Our method, even without fine-tuning, consistently outperforms previous structural pruning techniques across diverse model families, including Phi-2, LLaMA-2, LLaMA-3, and Qwen-2.5.

James Seale Smith, Chi-Heng Lin, Shikhar Tuli et al.

The rapid proliferation of large language models (LLMs) in natural language processing (NLP) has created a critical need for techniques that enable efficient deployment on memory-constrained devices without compromising performance. We present a method to prune LLMs that selectively prunes model blocks based on an importance score and replaces them with a low-parameter replacement strategy. Specifically, we propose a principled metric to replace each pruned block using a weight-sharing mechanism that leverages unpruned counterparts from the model and block-specific low-rank adapters. Furthermore, we facilitate the learning of these replacement blocks with output feature normalization and an adapter initialization scheme built on low-rank SVD reconstructions. Empirical evaluations demonstrate substantial performance gains over existing methods, achieving state-of-the-art performance on 5/6 benchmarks for a compression rate of 30% and 6/6 benchmarks for a compression rate of 40%. We also demonstrate that our approach can extend smaller models, boosting performance on 6/6 benchmarks using only ~0.3% tokens of extended training with minimal additional parameter costs.

Chen-Hao Chao, Wei-Fang Sun, Yen-Chang Hsu et al.

In this paper, we establish a connection between the parameterization of flow-based and energy-based generative models, and present a new flow-based modeling approach called energy-based normalizing flow (EBFlow). We demonstrate that by optimizing EBFlow with score-matching objectives, the computation of Jacobian determinants for linear transformations can be entirely bypassed. This feature enables the use of arbitrary linear layers in the construction of flow-based models without increasing the computational time complexity of each training iteration from $O(D^2L)$ to $O(D^3L)$ for an $L$-layered model that accepts $D$-dimensional inputs. This makes the training of EBFlow more efficient than the commonly-adopted maximum likelihood training method. In addition to the reduction in runtime, we enhance the training stability and empirical performance of EBFlow through a number of techniques developed based on our analysis of the score-matching methods. The experimental results demonstrate that our approach achieves a significant speedup compared to maximum likelihood estimation while outperforming prior methods with a noticeable margin in terms of negative log-likelihood (NLL).

James Seale Smith, Junjiao Tian, Shaunak Halbe et al.

Continual learning is a setting where machine learning models learn novel concepts from continuously shifting training data, while simultaneously avoiding degradation of knowledge on previously seen classes which may disappear from the training data for extended periods of time (a phenomenon known as the catastrophic forgetting problem). Current approaches for continual learning of a single expanding task (aka class-incremental continual learning) require extensive rehearsal of previously seen data to avoid this degradation of knowledge. Unfortunately, rehearsal comes at a cost to memory, and it may also violate data-privacy. Instead, we explore combining knowledge distillation and parameter regularization in new ways to achieve strong continual learning performance without rehearsal. Specifically, we take a deep dive into common continual learning techniques: prediction distillation, feature distillation, L2 parameter regularization, and EWC parameter regularization. We first disprove the common assumption that parameter regularization techniques fail for rehearsal-free continual learning of a single, expanding task. Next, we explore how to leverage knowledge from a pre-trained model in rehearsal-free continual learning and find that vanilla L2 parameter regularization outperforms EWC parameter regularization and feature distillation. Finally, we explore the recently popular ImageNet-R benchmark, and show that L2 parameter regularization implemented in self-attention blocks of a ViT transformer outperforms recent popular prompting for continual learning methods.

Ting Hua, Yilin Shen, Changsheng Zhao et al.

Domain classification is the fundamental task in natural language understanding (NLU), which often requires fast accommodation to new emerging domains. This constraint makes it impossible to retrain all previous domains, even if they are accessible to the new model. Most existing continual learning approaches suffer from low accuracy and performance fluctuation, especially when the distributions of old and new data are significantly different. In fact, the key real-world problem is not the absence of old data, but the inefficiency to retrain the model with the whole old dataset. Is it potential to utilize some old data to yield high accuracy and maintain stable performance, while at the same time, without introducing extra hyperparameters? In this paper, we proposed a hyperparameter-free continual learning model for text data that can stably produce high performance under various environments. Specifically, we utilize Fisher information to select exemplars that can "record" key information of the original model. Also, a novel scheme called dynamical weight consolidation is proposed to enable hyperparameter-free learning during the retrain process. Extensive experiments demonstrate that baselines suffer from fluctuated performance and therefore useless in practice. On the contrary, our proposed model CCFI significantly and consistently outperforms the best state-of-the-art method by up to 20% in average accuracy, and each component of CCFI contributes effectively to overall performance.

Yilin Shen, Yen-Chang Hsu, Avik Ray et al.

Intent classification is a major task in spoken language understanding (SLU). Since most models are built with pre-collected in-domain (IND) training utterances, their ability to detect unsupported out-of-domain (OOD) utterances has a critical effect in practical use. Recent works have shown that using extra data and labels can improve the OOD detection performance, yet it could be costly to collect such data. This paper proposes to train a model with only IND data while supporting both IND intent classification and OOD detection. Our method designs a novel domain-regularized module (DRM) to reduce the overconfident phenomenon of a vanilla classifier, achieving a better generalization in both cases. Besides, DRM can be used as a drop-in replacement for the last layer in any neural network-based intent classifier, providing a low-cost strategy for a significant improvement. The evaluation on four datasets shows that our method built on BERT and RoBERTa models achieves state-of-the-art performance against existing approaches and the strong baselines we created for the comparisons.

James Smith, Yen-Chang Hsu, Jonathan Balloch et al.

Modern computer vision applications suffer from catastrophic forgetting when incrementally learning new concepts over time. The most successful approaches to alleviate this forgetting require extensive replay of previously seen data, which is problematic when memory constraints or data legality concerns exist. In this work, we consider the high-impact problem of Data-Free Class-Incremental Learning (DFCIL), where an incremental learning agent must learn new concepts over time without storing generators or training data from past tasks. One approach for DFCIL is to replay synthetic images produced by inverting a frozen copy of the learner's classification model, but we show this approach fails for common class-incremental benchmarks when using standard distillation strategies. We diagnose the cause of this failure and propose a novel incremental distillation strategy for DFCIL, contributing a modified cross-entropy training and importance-weighted feature distillation, and show that our method results in up to a 25.1% increase in final task accuracy (absolute difference) compared to SOTA DFCIL methods for common class-incremental benchmarks. Our method even outperforms several standard replay based methods which store a coreset of images.

James Smith, Jonathan Balloch, Yen-Chang Hsu et al.

Rehearsal is a critical component for class-incremental continual learning, yet it requires a substantial memory budget. Our work investigates whether we can significantly reduce this memory budget by leveraging unlabeled data from an agent's environment in a realistic and challenging continual learning paradigm. Specifically, we explore and formalize a novel semi-supervised continual learning (SSCL) setting, where labeled data is scarce yet non-i.i.d. unlabeled data from the agent's environment is plentiful. Importantly, data distributions in the SSCL setting are realistic and therefore reflect object class correlations between, and among, the labeled and unlabeled data distributions. We show that a strategy built on pseudo-labeling, consistency regularization, Out-of-Distribution (OoD) detection, and knowledge distillation reduces forgetting in this setting. Our approach, DistillMatch, increases performance over the state-of-the-art by no less than 8.7% average task accuracy and up to 54.5% average task accuracy in SSCL CIFAR-100 experiments. Moreover, we demonstrate that DistillMatch can save up to 0.23 stored images per processed unlabeled image compared to the next best method which only saves 0.08. Our results suggest that focusing on realistic correlated distributions is a significantly new perspective, which accentuates the importance of leveraging the world's structure as a continual learning strategy.

Yen-Chang Hsu, Yilin Shen, Hongxia Jin et al.

Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise. Therefore, detecting whether an example is out-of-distribution (OoD) is crucial to enable a system that can reject such samples or alert users. Recent works have made significant progress on OoD benchmarks consisting of small image datasets. However, many recent methods based on neural networks rely on training or tuning with both in-distribution and out-of-distribution data. The latter is generally hard to define a-priori, and its selection can easily bias the learning. We base our work on a popular method ODIN, proposing two strategies for freeing it from the needs of tuning with OoD data, while improving its OoD detection performance. We specifically propose to decompose confidence scoring as well as a modified input pre-processing method. We show that both of these significantly help in detection performance. Our further analysis on a larger scale image dataset shows that the two types of distribution shifts, specifically semantic shift and non-semantic shift, present a significant difference in the difficulty of the problem, providing an analysis of when ODIN-like strategies do or do not work.

Yen-Chang Hsu, Zhaoyang Lv, Joel Schlosser et al.

This work presents a new strategy for multi-class classification that requires no class-specific labels, but instead leverages pairwise similarity between examples, which is a weaker form of annotation. The proposed method, meta classification learning, optimizes a binary classifier for pairwise similarity prediction and through this process learns a multi-class classifier as a submodule. We formulate this approach, present a probabilistic graphical model for it, and derive a surprisingly simple loss function that can be used to learn neural network-based models. We then demonstrate that this same framework generalizes to the supervised, unsupervised cross-task, and semi-supervised settings. Our method is evaluated against state of the art in all three learning paradigms and shows a superior or comparable accuracy, providing evidence that learning multi-class classification without multi-class labels is a viable learning option.

Yen-Chang Hsu, Zhaoyang Lv, Joel Schlosser et al.

Neural network-based clustering has recently gained popularity, and in particular a constrained clustering formulation has been proposed to perform transfer learning and image category discovery using deep learning. The core idea is to formulate a clustering objective with pairwise constraints that can be used to train a deep clustering network; therefore the cluster assignments and their underlying feature representations are jointly optimized end-to-end. In this work, we provide a novel clustering formulation to address scalability issues of previous work in terms of optimizing deeper networks and larger amounts of categories. The proposed objective directly minimizes the negative log-likelihood of cluster assignment with respect to the pairwise constraints, has no hyper-parameters, and demonstrates improved scalability and performance on both supervised learning and unsupervised transfer learning.

Yen-Chang Hsu, Zheng Xu, Zsolt Kira et al.

This work proposed a novel learning objective to train a deep neural network to perform end-to-end image pixel clustering. We applied the approach to instance segmentation, which is at the intersection of image semantic segmentation and object detection. We utilize the most fundamental property of instance labeling -- the pairwise relationship between pixels -- as the supervision to formulate the learning objective, then apply it to train a fully convolutional network (FCN) for learning to perform pixel-wise clustering. The resulting clusters can be used as the instance labeling directly. To support labeling of an unlimited number of instance, we further formulate ideas from graph coloring theory into the proposed learning objective. The evaluation on the Cityscapes dataset demonstrates strong performance and therefore proof of the concept. Moreover, our approach won the second place in the lane detection competition of 2017 CVPR Autonomous Driving Challenge, and was the top performer without using external data.

Yen-Chang Hsu, Zhaoyang Lv, Zsolt Kira

This paper introduces a novel method to perform transfer learning across domains and tasks, formulating it as a problem of learning to cluster. The key insight is that, in addition to features, we can transfer similarity information and this is sufficient to learn a similarity function and clustering network to perform both domain adaptation and cross-task transfer learning. We begin by reducing categorical information to pairwise constraints, which only considers whether two instances belong to the same class or not. This similarity is category-agnostic and can be learned from data in the source domain using a similarity network. We then present two novel approaches for performing transfer learning using this similarity function. First, for unsupervised domain adaptation, we design a new loss function to regularize classification with a constrained clustering loss, hence learning a clustering network with the transferred similarity metric generating the training inputs. Second, for cross-task learning (i.e., unsupervised clustering with unseen categories), we propose a framework to reconstruct and estimate the number of semantic clusters, again using the clustering network. Since the similarity network is noisy, the key is to use a robust clustering algorithm, and we show that our formulation is more robust than the alternative constrained and unconstrained clustering approaches. Using this method, we first show state of the art results for the challenging cross-task problem, applied on Omniglot and ImageNet. Our results show that we can reconstruct semantic clusters with high accuracy. We then evaluate the performance of cross-domain transfer using images from the Office-31 and SVHN-MNIST tasks and present top accuracy on both datasets. Our approach doesn't explicitly deal with domain discrepancy. If we combine with a domain adaptation loss, it shows further improvement.

Zheng Xu, Yen-Chang Hsu, Jiawei Huang

There is an increasing interest on accelerating neural networks for real-time applications. We study the student-teacher strategy, in which a small and fast student network is trained with the auxiliary information learned from a large and accurate teacher network. We propose to use conditional adversarial networks to learn the loss function to transfer knowledge from teacher to student. The proposed method is particularly effective for relatively small student networks. Moreover, experimental results show the effect of network size when the modern networks are used as student. We empirically study the trade-off between inference time and classification accuracy, and provide suggestions on choosing a proper student network.

Yen-Chang Hsu, Zhaoyang Lv, Zsolt Kira

Automatically discovering image categories in unlabeled natural images is one of the important goals of unsupervised learning. However, the task is challenging and even human beings define visual categories based on a large amount of prior knowledge. In this paper, we similarly utilize prior knowledge to facilitate the discovery of image categories. We present a novel end-to-end network to map unlabeled images to categories as a clustering network. We propose that this network can be learned with contrastive loss which is only based on weak binary pair-wise constraints. Such binary constraints can be learned from datasets in other domains as transferred similarity functions, which mimic a simple knowledge transfer. We first evaluate our experiments on the MNIST dataset as a proof of concept, based on predicted similarities trained on Omniglot, showing a 99\% accuracy which significantly outperforms clustering based approaches. Then we evaluate the discovery performance on Cifar-10, STL-10, and ImageNet, which achieves both state-of-the-art accuracy and shows it can be scalable to various large natural images.

Yen-Chang Hsu, Zsolt Kira

This paper presents a neural network-based end-to-end clustering framework. We design a novel strategy to utilize the contrastive criteria for pushing data-forming clusters directly from raw data, in addition to learning a feature embedding suitable for such clustering. The network is trained with weak labels, specifically partial pairwise relationships between data instances. The cluster assignments and their probabilities are then obtained at the output layer by feed-forwarding the data. The framework has the interesting characteristic that no cluster centers need to be explicitly specified, thus the resulting cluster distribution is purely data-driven and no distance metrics need to be predefined. The experiments show that the proposed approach beats the conventional two-stage method (feature embedding with k-means) by a significant margin. It also compares favorably to the performance of the standard cross entropy loss for classification. Robustness analysis also shows that the method is largely insensitive to the number of clusters. Specifically, we show that the number of dominant clusters is close to the true number of clusters even when a large k is used for clustering.